
import pandas as pd
import numpy as np                     # For mathematical calculations
import seaborn as sns                  # For data visualization
import matplotlib.pyplot as plt 
import seaborn as sn                   # For plotting graphs
import io
%matplotlib inline
import warnings                        # To ignore any warnings
warnings.filterwarnings("ignore")


filepath2 = r"C:\Users\91623\OneDrive\Desktop\zomato project\final\data1.xlsx"
df= pd.read_excel(filepath2)
print(df)

                    NAME   PRICE  \
0                Hitchki  1200.0   
1           Baba Falooda   400.0   
2          Chin Chin Chu  1800.0   
3         Butterfly High  1000.0   
4              BKC  DIVE  1200.0   
...                  ...     ...   
11523  Hari Om Snack Bar   350.0   
11524           PitaBurg   400.0   
11525     Uncha Otlawala   300.0   
11526     Mandarin Panda   400.0   
11527                NaN     NaN   

                                         CUSINE_CATEGORY  \
0      Modern Indian,North Indian,Chinese,Momos,Birya...   
1                           Desserts,Ice Cream,Beverages   
2                                          Asian,Chinese   
3                                          Modern Indian   
4                       North Indian,Chinese,Continental   
...                                                  ...   
11523                     Fast Food,South Indian,Chinese   
11524                                 Fast Food,Lebanese   
11525                                 Desserts,Ice Cream   
11526                              Desserts,Chinese,Thai   
11527                                                NaN   

                                                  REGION     CUSINE TYPE  \
0      First International Financial Centre-- Bandra ...   Casual Dining   
1                                                  Mahim  Dessert Parlor   
2                                                   Juhu   Casual Dining   
3                                   Bandra Kurla Complex             Bar   
4                                   Bandra Kurla Complex             Bar   
...                                                  ...             ...   
11523                                     Kandivali West     Quick Bites   
11524                                        Lower Parel            none   
11525                                     Kandivali West  Dessert Parlor   
11526                                         Malad West            none   
11527                                                NaN             NaN   

       RATING_TYPE RATING VOTES  
0        Excellent    4.9  3529  
1        Very Good    4.4  1723  
2        Very Good    4.2   337  
3        Very Good    4.3  1200  
4      Veľmi dobré    4.4  5995  
...            ...    ...   ...  
11523         Good    3.7    64  
11524      Average    3.4    99  
11525         Good    3.5    29  
11526         Good    3.7   121  
11527          NaN    NaN   NaN  

[11528 rows x 8 columns]


df.head()


unique = [feature for feature in df.columns if len(df[feature].unique())>0 and len(df[feature].unique())<100]
for feature in unique:
    print("{} has {} unique values : {} {}".format(feature,len(df[feature].unique()),df[feature].unique(),"\n"))

PRICE has 64 unique values : [1200.  400. 1800. 1000.  800. 1300. 1500.  600. 1400. 1100. 2000.  350.
  900.  700.  500. 1600.  150.  300.  550.  450.  650.  750.  250.  200.
  850.  100. 2500. 1450.  180.  950. 1700. 1900. 2600. 2400. 3000. 1250.
 3200.  505. 2200. 1050. 1650. 1350.   50.  920. 1150. 1550. 3500.  398.
 5000.  120.  160.    5.  480. 2100.  580. 1850.  220.  249. 2300.    0.
  360.  248. 2700.   nan] 

CUSINE TYPE has 23 unique values : ['Casual Dining' 'Dessert Parlor' 'Bar' 'Café' 'Quick Bites' 'none'
 'Bakery' 'Sweet Shop' 'Food Court' 'Fine Dining' 'Beverage Shop' 'Pub'
 'Food Truck' 'Dhaba' 'Lounge' 'Kiosk' 'Microbrewery' 'Paan Shop'
 'Irani Cafe' 'Confectionery' 'Mess' 'Bhojanalya' nan] 

RATING_TYPE has 31 unique values : ['Excellent' 'Very Good' 'Veľmi dobré' 'Good' 'Velmi dobré' 'None'
 'Average' 'Excelente' 'Muito Bom' 'Poor' 'Skvělá volba' 'Çok iyi' 'Baik'
 'Bardzo dobrze' 'Bom' 'Média' 'Dobrze' 'Buono' 'İyi' 'Bueno' 'Ortalama'
 'Skvělé' 'Biasa' 'Průměr' 'Sangat Baik' 'Priemer' 'Dobré' 'Promedio'
 'Muy Bueno' 'Media' nan] 

RATING has 34 unique values : ['4.9' '4.4' '4.2' '4.3' '4.5' '4.7' '4.0' '4.6' '4.1' '3.9' '3.8' '3.6'
 'NEW' '3.4' '3.0' '3.7' '4.8' '3.3' '3.5' '3.2' '3.1' '2.7' '2.5' '2.8'
 '2.6' '2.3' '2.9' '2.4' 'Opening' '2.1' '2.2' '1.8' '2.0' nan]


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 11528 entries, 0 to 11527
Data columns (total 8 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   NAME             11527 non-null  object 
 1   PRICE            11527 non-null  float64
 2   CUSINE_CATEGORY  11526 non-null  object 
 3   REGION           11527 non-null  object 
 4   CUSINE TYPE      11527 non-null  object 
 5   RATING_TYPE      11527 non-null  object 
 6   RATING           11527 non-null  object 
 7   VOTES            11527 non-null  object 
dtypes: float64(1), object(7)
memory usage: 720.6+ KB


df.shape

(11528, 8)


df.columns = df.columns.str.lower()

df


df.isnull().sum()

name               1
price              1
cusine_category    2
region             1
cusine type        1
rating_type        1
rating             1
votes              1
dtype: int64


df= df.dropna()


df.isnull().sum()

name               0
price              0
cusine_category    0
region             0
cusine type        0
rating_type        0
rating             0
votes              0
dtype: int64


unique = [feature for feature in df.columns if len(df[feature].unique())>0 and len(df[feature].unique())<100]
for feature in unique:
    print("{} has {} unique values : {} {}".format(feature,len(df[feature].unique()),df[feature].unique(),"\n"))

price has 63 unique values : [1200.  400. 1800. 1000.  800. 1300. 1500.  600. 1400. 1100. 2000.  350.
  900.  700.  500. 1600.  150.  300.  550.  450.  650.  750.  250.  200.
  850.  100. 2500. 1450.  180.  950. 1700. 1900. 2600. 2400. 3000. 1250.
 3200.  505. 2200. 1050. 1650. 1350.   50.  920. 1150. 1550. 3500.  398.
 5000.  120.  160.    5.  480. 2100.  580. 1850.  220.  249. 2300.    0.
  360.  248. 2700.] 

cusine type has 22 unique values : ['Casual Dining' 'Dessert Parlor' 'Bar' 'Café' 'Quick Bites' 'none'
 'Bakery' 'Sweet Shop' 'Food Court' 'Fine Dining' 'Beverage Shop' 'Pub'
 'Food Truck' 'Dhaba' 'Lounge' 'Kiosk' 'Microbrewery' 'Paan Shop'
 'Irani Cafe' 'Confectionery' 'Mess' 'Bhojanalya'] 

rating_type has 30 unique values : ['Excellent' 'Very Good' 'Veľmi dobré' 'Good' 'Velmi dobré' 'None'
 'Average' 'Excelente' 'Muito Bom' 'Poor' 'Skvělá volba' 'Çok iyi' 'Baik'
 'Bardzo dobrze' 'Bom' 'Média' 'Dobrze' 'Buono' 'İyi' 'Bueno' 'Ortalama'
 'Skvělé' 'Biasa' 'Průměr' 'Sangat Baik' 'Priemer' 'Dobré' 'Promedio'
 'Muy Bueno' 'Media'] 

rating has 33 unique values : ['4.9' '4.4' '4.2' '4.3' '4.5' '4.7' '4.0' '4.6' '4.1' '3.9' '3.8' '3.6'
 'NEW' '3.4' '3.0' '3.7' '4.8' '3.3' '3.5' '3.2' '3.1' '2.7' '2.5' '2.8'
 '2.6' '2.3' '2.9' '2.4' 'Opening' '2.1' '2.2' '1.8' '2.0']


df['rating_type'].replace(to_replace='Excelente' , value='Excellent', inplace=True)
df['rating_type'].replace(to_replace=['Veľmi dobré','Bardzo dobrze','Muy Bueno','Velmi dobré'] , value='Very Good', inplace=True)
df['rating_type'].replace(to_replace=['Skvělá volba','Dobrze','Bueno','Buono','Dobré','Bom','Skvělé'] , value='Good', inplace=True)
df['rating_type'].replace(to_replace=['Priemer','Média','Çok iyi'] , value='Average', inplace=True)
df['rating_type'].replace(to_replace=['Průměr','Promedio','Ortalama','Muito Bom','İyi'] , value='Poor', inplace=True)
df['rating_type'].replace(to_replace=['Baik','Biasa','Media','Sangat Baik'] , value='Very Poor', inplace=True)

df


df.head()


unique = [feature for feature in df.columns if len(df[feature].unique())>0 and len(df[feature].unique())<100]
for feature in unique:
    print("{} has {} unique values : {} {}".format(feature,len(df[feature].unique()),df[feature].unique(),"\n"))

price has 63 unique values : [1200.  400. 1800. 1000.  800. 1300. 1500.  600. 1400. 1100. 2000.  350.
  900.  700.  500. 1600.  150.  300.  550.  450.  650.  750.  250.  200.
  850.  100. 2500. 1450.  180.  950. 1700. 1900. 2600. 2400. 3000. 1250.
 3200.  505. 2200. 1050. 1650. 1350.   50.  920. 1150. 1550. 3500.  398.
 5000.  120.  160.    5.  480. 2100.  580. 1850.  220.  249. 2300.    0.
  360.  248. 2700.] 

cusine type has 22 unique values : ['Casual Dining' 'Dessert Parlor' 'Bar' 'Café' 'Quick Bites' 'none'
 'Bakery' 'Sweet Shop' 'Food Court' 'Fine Dining' 'Beverage Shop' 'Pub'
 'Food Truck' 'Dhaba' 'Lounge' 'Kiosk' 'Microbrewery' 'Paan Shop'
 'Irani Cafe' 'Confectionery' 'Mess' 'Bhojanalya'] 

rating_type has 7 unique values : ['Excellent' 'Very Good' 'Good' 'None' 'Average' 'Poor' 'Very Poor'] 

rating has 33 unique values : ['4.9' '4.4' '4.2' '4.3' '4.5' '4.7' '4.0' '4.6' '4.1' '3.9' '3.8' '3.6'
 'NEW' '3.4' '3.0' '3.7' '4.8' '3.3' '3.5' '3.2' '3.1' '2.7' '2.5' '2.8'
 '2.6' '2.3' '2.9' '2.4' 'Opening' '2.1' '2.2' '1.8' '2.0']


df.columns = df.columns.str.lower()


df['region'] = df['region'].str.replace('[a-zA-Z].+-- ','',regex=True)


df['region'] = df['region'].str.replace(' West| west| East| east','',regex=True)


df.region.unique()

array(['Bandra Kurla Complex', 'Mahim', 'Juhu', 'Flea Bazaar Café',
       'Marol', 'Andheri', 'Kamala Mills Compound', 'Dadar', 'Khar',
       'Lower Parel', 'Bandra', 'Mumbai CST Area', 'Bhandup', 'Malad',
       'Powai', 'Chembur', 'Goregaon', 'Vile Parle', 'CBD-Belapur',
       'Borivali', 'Near Andheri Station', 'Vasai', 'Thane', 'Parel',
       'Colaba', 'Nariman Point', 'Santacruz', 'Mulund', 'Kandivali',
       'Mahakali', 'Airoli', 'Mira Road', 'Fort', 'Ghodbunder Road',
       'Jogeshwari', 'Vashi', 'Ghatkopar', 'Sakinaka', '7 Andheri',
       'Byculla', 'Kalyan', 'Bhayandar', 'Charni Road', 'Chandivali',
       'Kurla', 'Mohammad Ali Road', 'Kharghar', 'Matunga', 'Worli',
       'Dadar Shivaji Park', 'Azad Nagar', 'Ulhasnagar', '4 Bungalows',
       'Kopar Khairane', 'Dahisar', 'Seawoods', 'Mumbai Central',
       'Veera Desai Area', 'Chowpatty', 'Old Panvel', 'Sion', 'Tardeo',
       'Mazgaon', 'Prabhadevi', 'Sanpada', 'Ghansoli', 'Virar', 'Girgaum',
       'Mumbra', 'Marve', 'Kamothe', 'Chakala', 'Ulwe', 'Marine Lines',
       'Mahalaxmi', 'Runwal Green', 'Nalasopara', 'Kalwa', 'Nerul',
       'Grant Road', 'Breach Candy', 'New Panvel', 'Churchgate',
       'Vikhroli', 'Kalbadevi', 'Dombivali', 'Kemps Corner',
       'Malabar Hill', 'Turbhe', 'Kalamboli', 'Wadala', 'Alibaug',
       'Peddar Road', 'Ambernath', 'Gorai', 'Majiwada', 'Sewri',
       'CBD Belapur', 'Cuffe Parade', 'Girgaon Chowpatty', 'Panvel',
       'Trombay'], dtype=object)


df['region'] = df['region'].str.replace('4 Bungalows|7 Andheri|Azad Nagar|Near Andheri Station|Veera Desai Area|Mahakali','Andheri',regex=True)
df['region'] = df['region'].str.replace('Bandra Kurla Complex','Bandra',regex=True)
df['region'] = df['region'].str.replace('CBD-Belapur','Belapur',regex=True)
df['region'] = df['region'].str.replace('Girgaon Chowpatty','Chowpatty',regex=True)
df['region'] = df['region'].str.replace('Dadar Shivaji Park','Dadar',regex=True)
df['region'] = df['region'].str.replace('Flea Bazaar Café|Kamala Mills Compound','Lower Parel',regex=True)
df['region'] = df['region'].str.replace('Runwal Green','Mulund',regex=True)
df['region'] = df['region'].str.replace('Mumbai CST Area','Mumbai Central',regex=True)
df['region'] = df['region'].str.replace('Kopar Khairane|Seawoods|Turbhe|Ulwe','Navi Mumbai',regex=True)
df['region'] = df['region'].str.replace('New Panvel|Old Panvel','Panvel',regex=True)
df['region'] = df['region'].str.replace('Kamothe','Sion',regex=True)
df['region'] = df['region'].str.replace('Ghodbunder Road|Majiwada','Thane',regex=True)


df.region.unique()

array(['Bandra', 'Mahim', 'Juhu', 'Lower Parel', 'Marol', 'Andheri',
       'Dadar', 'Khar', 'Mumbai Central', 'Bhandup', 'Malad', 'Powai',
       'Chembur', 'Goregaon', 'Vile Parle', 'Belapur', 'Borivali',
       'Vasai', 'Thane', 'Parel', 'Colaba', 'Nariman Point', 'Santacruz',
       'Mulund', 'Kandivali', 'Airoli', 'Mira Road', 'Fort', 'Jogeshwari',
       'Vashi', 'Ghatkopar', 'Sakinaka', 'Byculla', 'Kalyan', 'Bhayandar',
       'Charni Road', 'Chandivali', 'Kurla', 'Mohammad Ali Road',
       'Kharghar', 'Matunga', 'Worli', 'Ulhasnagar', 'Navi Mumbai',
       'Dahisar', 'Chowpatty', 'Panvel', 'Sion', 'Tardeo', 'Mazgaon',
       'Prabhadevi', 'Sanpada', 'Ghansoli', 'Virar', 'Girgaum', 'Mumbra',
       'Marve', 'Chakala', 'Marine Lines', 'Mahalaxmi', 'Nalasopara',
       'Kalwa', 'Nerul', 'Grant Road', 'Breach Candy', 'Churchgate',
       'Vikhroli', 'Kalbadevi', 'Dombivali', 'Kemps Corner',
       'Malabar Hill', 'Kalamboli', 'Wadala', 'Alibaug', 'Peddar Road',
       'Ambernath', 'Gorai', 'Sewri', 'CBD Belapur', 'Cuffe Parade',
       'Trombay'], dtype=object)


df.isnull().sum()

name               0
price              0
cusine_category    0
region             0
cusine type        0
rating_type        0
rating             0
votes              0
dtype: int64


df['votes'].replace(to_replace=['-','new','opening'], value='0', inplace=True)


df.votes.unique()

array(['3529', '1723', '337', ..., '944', '861', '1249'], dtype=object)


df.head()


df.describe()


df['rating'].unique()

array(['4.9', '4.4', '4.2', '4.3', '4.5', '4.7', '4.0', '4.6', '4.1',
       '3.9', '3.8', '3.6', 'NEW', '3.4', '3.0', '3.7', '4.8', '3.3',
       '3.5', '3.2', '3.1', '2.7', '2.5', '2.8', '2.6', '2.3', '2.9',
       '2.4', 'Opening', '2.1', '2.2', '1.8', '2.0'], dtype=object)


df['rating'].replace(to_replace=['-','NEW','Opening'], value='0', inplace=True)


df['votes'].replace(to_replace=['-','NEW','Opening'], value='0', inplace=True)


df['rating'].unique()

array(['4.9', '4.4', '4.2', '4.3', '4.5', '4.7', '4.0', '4.6', '4.1',
       '3.9', '3.8', '3.6', '0', '3.4', '3.0', '3.7', '4.8', '3.3', '3.5',
       '3.2', '3.1', '2.7', '2.5', '2.8', '2.6', '2.3', '2.9', '2.4',
       '2.1', '2.2', '1.8', '2.0'], dtype=object)


df['rating']=df['rating'].astype(float)


df['votes']=df['votes'].astype(float)


df.describe()


numerical_features = [feature for feature in df.columns if df[feature].dtype != "O"]
print("we have {} numerical features out of {}".format(len(numerical_features),len(df.columns)))

we have 3 numerical features out of 8


discrete_features = [feature for feature in numerical_features if len(df[feature].unique())<25]
print("we have {} discrete features out of {} total features".format(len(discrete_features),len(df.columns)))

we have 0 discrete features out of 8 total features


continuos_features = [feature for feature in numerical_features if feature not in discrete_features]
print("we have {} continuos features out of {} total features".format(len(continuos_features),len(df.columns)))

we have 3 continuos features out of 8 total features


fig,ax = plt.subplots(3,3,figsize=(20,12))
for variable, subplot in zip(continuos_features,ax.flatten()):
    sns.histplot(df[variable],ax=subplot)


sns.boxplot(df['price'])
plt.title("price- Before outlier removal");


df = df.drop(df[df['price']>3000].index)


sns.boxplot(df['price'])
plt.title("price- after outlier removal");


sns.scatterplot(data =df['votes'])
plt.title("votes- Before outlier removal");


df = df.drop(df[df['votes']>6000].index)


sns.scatterplot(data =df['votes'])
plt.title("votes- Before outlier removal");


df = df.drop(df[df['votes']>4000].index)


sns.scatterplot(data =df['votes'])
plt.title("votes- Before outlier removal");


fig,ax = plt.subplots(3,3,figsize=(20,12))
for variable, subplot in zip(continuos_features,ax.flatten()):
    sns.histplot(df[variable],ax=subplot,palette="cool")


import plotly.express as px
import plotly.graph_objects as go
fig = px.histogram(df, x='cusine type', color='cusine type', 
             title= 'No. of Restaurants by Cuisine Type', 
             labels={'CUSINE TYPE':'Cuisine Type'})

fig.show()


import plotly.express as px
import plotly.graph_objects as go
fig = px.histogram(df, x='cusine type', color='rating',
             title= 'No. of Restaurants by Cuisine Type', 
             labels={'CUSINE TYPE':'Cuisine Type'})

fig.show()


df['rates'] = df['rating'].apply(np.floor)


df.head()


import plotly.express as px
import plotly.graph_objects as go
fig = px.histogram(df, x='cusine type', color='rates',
             title= 'No. of Restaurants by Cuisine Type', 
             labels={'CUSINE TYPE':'Cuisine Type'})

fig.show()


rating_type_df = df['rating_type'].value_counts().reset_index()
rating_type_df.rename(columns={'index':'RATING TYPE', 'RATING_TYPE':'COUNT OF RESTAURANTS'}, inplace=True)
rating_type_df


fig = px.pie(rating_type_df, names='RATING TYPE', values='rating_type', color='rating_type', 
       title='Percentage of Restaurants by Rating Type').update_traces(textposition='inside', textinfo='percent+label')

fig.show()


seafood_df = df[df['cusine_category'].str.contains('Seafood')]
seafood_df.sort_values(by='rating',ascending=False).head(10)


foodtruck_df = df[df['cusine type'] == 'Food Truck']
foodtruck_df.sort_values(by='rating',ascending=False).head(2)


corrmat=df.corr()
top_corr=corrmat.index
plt.figure(figsize=(20,20))
g= sns.heatmap(df[top_corr].corr(),annot= True,cmap="RdYlGn")


pos_corrmat = df.corr()
filtereddf = pos_corrmat[((pos_corrmat >= .5) & (pos_corrmat !=1.000))]
plt.figure(figsize=(15,5))
sns.heatmap(filtereddf, annot=True, cmap="Reds")
plt.title('Positive correlation matrix')
plt.show()


neg_corrmat = df.corr()
filtereddf = neg_corrmat[((neg_corrmat <-.3) & (neg_corrmat !=1.000))]
plt.figure(figsize=(15,5))
sns.heatmap(filtereddf, annot=True, cmap="Reds")
plt.title('Negative correlation matrix')
plt.show()


sns.pairplot(df,hue='rating')

<seaborn.axisgrid.PairGrid at 0x1e9a94c7e50>


df1=df.drop(['name'],axis=1)


df1=df.drop(['rates'],axis=1)

df1


from sklearn.preprocessing import LabelEncoder
le=LabelEncoder()


list1=['cusine type','region','cusine_category','rating_type']
for i in list1:
    df1[i]=le.fit_transform(df1[i])

df1.head()


df1.head()
df1=df1.drop('name',axis=1)


df1.shape

(11504, 7)


df1.dropna(how='any',inplace=True)
df1.shape

(11504, 7)


f1=df1.drop(['rating'],axis=1)


f1.head()


f1.dtypes

price              float64
cusine_category      int32
region               int32
cusine type          int32
rating_type          int32
votes              float64
dtype: object


df['rating'].unique()

array([4.9, 4.4, 4.2, 4.3, 4.5, 4.7, 4. , 4.1, 3.9, 3.8, 3.6, 0. , 3.4,
       3. , 4.6, 3.7, 4.8, 3.3, 3.5, 3.2, 3.1, 2.7, 2.5, 2.8, 2.6, 2.3,
       2.9, 2.4, 2.1, 2.2, 1.8, 2. ])


label=df['rating'].values
label

array([4.9, 4.4, 4.2, ..., 3.4, 3.5, 3.7])


from sklearn.preprocessing import StandardScaler
ss=StandardScaler()

f1


f1=StandardScaler().fit(f1).transform(f1)
f1

array([[ 2.30626764,  0.47160834, -1.39899677, -0.90583168, -0.32650302,
         9.86040944],
       [-0.34125157, -0.44329655,  0.17220868, -0.6414244 ,  2.20327688,
         4.58592752],
       [ 4.29190705, -1.68312094, -0.31123915, -0.90583168,  2.20327688,
         0.53806929],
       ...,
       [-0.34125157, -0.23808424,  0.09163404,  1.20942659, -0.95894799,
        -0.15701747],
       [-0.67219147, -0.44451805, -0.10980256, -0.6414244 ,  0.30594196,
        -0.36145475],
       [-0.34125157, -0.45184707,  0.25278332,  1.20942659,  0.30594196,
        -0.09276575]])


from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(f1,label,test_size=0.,random_state=22)


X_train.shape,X_test.shape,y_train.shape,y_test.shape

((10353, 6), (1151, 6), (10353,), (1151,))


from sklearn.linear_model import LinearRegression
lin_reg=LinearRegression()
lin_reg

LinearRegression()


lin_reg.fit(X_train,y_train)

LinearRegression()


print(lin_reg.score(X_train,y_train))
print(lin_reg.score(X_test,y_test))

0.1414453027302125
0.1490038246780161


lin_reg_pred=lin_reg.predict(X_test)


from sklearn.metrics import r2_score
lin_reg_score=r2_score(y_test,lin_reg_pred)*100
print("Accuracy score for LR :",lin_reg_score)

Accuracy score for LR : 14.90038246780161


from sklearn.linear_model import Ridge


rr=Ridge()
rr

Ridge()


rr.fit(X_train,y_train)

Ridge()


print(rr.score(X_train,y_train))
print(rr.score(X_test,y_test))

0.1414453009753005
0.14900268869513744


rr_pred=rr.predict(X_test)


from sklearn.metrics import r2_score
rr_score=r2_score(y_test,rr_pred)*100
print("Accuracy score for RidgeR :",rr_score)

Accuracy score for RidgeR : 14.900268869513745


from sklearn.linear_model import Lasso


lr=Lasso()
lr

Lasso()


lr.fit(X_train,y_train)

Lasso()


print(lr.score(X_train,y_train))
print(lr.score(X_test,y_test))

0.0
-0.00011737831711000624


lr_pred=lr.predict(X_test)


from sklearn.metrics import r2_score

lr_score=r2_score(y_test,lr_pred)*100
print("Accuracy score for LR :",lr_score)

Accuracy score for LR : -0.011737831711000624


from sklearn.ensemble import RandomForestRegressor


rfr=RandomForestRegressor()
rfr

RandomForestRegressor()


rfr.fit(X_train,y_train)

RandomForestRegressor()


print(rfr.score(X_train,y_train))
print(rfr.score(X_test,y_test))

0.9960612633562352
0.9747745012100493


rfr_pred=rfr.predict(X_test)


from sklearn.metrics import r2_score

rfr_score=r2_score(y_test,rfr_pred)*100
print("Accuracy score for LR :",rfr_score)

Accuracy score for LR : 97.47745012100492


from sklearn.svm import SVR


svr=SVR()
svr.fit(X_train,y_train)

SVR()


print(svr.score(X_train,y_train))
print(svr.score(X_test,y_test))

0.884537566795772
0.8932078931357496


svr_pred=svr.predict(X_test)


from sklearn.metrics import r2_score

svr_score=r2_score(y_test,svr_pred)*100
print("Accuracy score for LR :",svr_score)

Accuracy score for LR : 89.32078931357495


pd.DataFrame({"Model Names":['Linear Reg','Ridge Reg','Lasso Reg','RandomForest Reg','Support Vector Reg'],
            "Accuracy socre":[lin_reg_score,rr_score,lr_score,rfr_score,svr_score]})

f1

array([[ 2.30626764,  0.47160834, -1.39899677, -0.90583168, -0.32650302,
         9.86040944],
       [-0.34125157, -0.44329655,  0.17220868, -0.6414244 ,  2.20327688,
         4.58592752],
       [ 4.29190705, -1.68312094, -0.31123915, -0.90583168,  2.20327688,
         0.53806929],
       ...,
       [-0.34125157, -0.23808424,  0.09163404,  1.20942659, -0.95894799,
        -0.15701747],
       [-0.67219147, -0.44451805, -0.10980256, -0.6414244 ,  0.30594196,
        -0.36145475],
       [-0.34125157, -0.45184707,  0.25278332,  1.20942659,  0.30594196,
        -0.09276575]])


rfr.predict([[1.3,0.7,1,1,0.234,7]])

array([3.894])


sample=pd.DataFrame({"Actual Ratin":y_test,
             "Predicted Rating":np.round(rfr_pred,2)})
sample


sample.to_csv("Model Prediction Sample.csv",index=False)

	price
count	11526.000000
mean	505.309301
std	309.650892
min	0.000000
25%	300.000000
50%	450.000000
75%	600.000000
max	5000.000000

	price	rating	votes
count	11526.000000	11526.000000	11526.000000
mean	505.309301	3.179108	162.204060
std	309.650892	1.043701	416.886777
min	0.000000	0.000000	0.000000
25%	300.000000	3.100000	11.000000
50%	450.000000	3.400000	37.000000
75%	600.000000	3.700000	130.000000
max	5000.000000	4.900000	10217.000000

ridge¶

lasso¶

Random Forest Regressor¶

vector¶

	NAME	PRICE	CUSINE_CATEGORY	REGION	CUSINE TYPE	RATING_TYPE	RATING	VOTES
0	Hitchki	1200.0	Modern Indian,North Indian,Chinese,Momos,Birya...	First International Financial Centre-- Bandra ...	Casual Dining	Excellent	4.9	3529
1	Baba Falooda	400.0	Desserts,Ice Cream,Beverages	Mahim	Dessert Parlor	Very Good	4.4	1723
2	Chin Chin Chu	1800.0	Asian,Chinese	Juhu	Casual Dining	Very Good	4.2	337
3	Butterfly High	1000.0	Modern Indian	Bandra Kurla Complex	Bar	Very Good	4.3	1200
4	BKC DIVE	1200.0	North Indian,Chinese,Continental	Bandra Kurla Complex	Bar	Veľmi dobré	4.4	5995

	RATING TYPE	rating_type
0	Average	4983
1	Good	4260
2	Very Good	1129
3	None	979
4	Excellent	93
5	Poor	56
6	Very Poor	4

	name	price	cusine_category	region	cusine type	rating_type	rating	votes	rates
6172	Thangabali	1000.0	Seafood,South Indian,Mangalorean,Andhra,Kerala	Khar	Bar	Excellent	4.7	564.0	4.0
70	Ceremonial Kitchen & Co	1000.0	Seafood,Maharashtrian,North Indian,Chinese	Thane	Casual Dining	Excellent	4.6	350.0	4.0
10435	Maharashtra Lunch Home	600.0	Maharashtrian,Malwani,Konkan,Seafood	Kharghar	Casual Dining	Excellent	4.6	209.0	4.0
3139	Peco Peco	700.0	Chinese,Seafood,Asian	Powai	none	Excellent	4.5	497.0	4.0
10086	Quarter Canteen	1100.0	North Indian,Seafood,Chinese	Bandra	Casual Dining	Excellent	4.5	573.0	4.0
8511	Pi Bar and Kitchen	1600.0	Continental,European,Italian,Seafood,Pizza,Des...	Andheri	Bar	Excellent	4.5	2068.0	4.0
833	The Harbour Bay - SeaFood Kitchen & Bar	2400.0	Seafood,Beverages	Bandra	Casual Dining	Excellent	4.5	100.0	4.0
816	Rajmanya- Seafood family restaurant	800.0	Maharashtrian,Konkan,Seafood	Vashi	Casual Dining	Excellent	4.5	178.0	4.0
845	Monis Bar and Restaurant	1000.0	North Indian,Chinese,Continental,Seafood,Bever...	Thane	Casual Dining	Very Good	4.4	662.0	4.0
312	Zesty Kitchen	600.0	North Indian,Maharashtrian,Konkan,Mangalorean,...	Chandivali	Casual Dining	Very Good	4.4	191.0	4.0

	name	price	cusine_category	region	cusine type	rating_type	rating	votes	rates
241	Dumpling Delights	200.0	Momos	Matunga	Food Truck	Very Good	4.3	212.0	4.0
940	Street Food Co.	250.0	Fast Food,Chinese	Virar	Food Truck	Very Good	4.1	274.0	4.0

	name	price	cusine_category	region	cusine type	rating_type	rating	votes
0	Hitchki	1200.0	1821	4	5	1	4.9	3529.0
1	Baba Falooda	400.0	1072	43	7	5	4.4	1723.0
2	Chin Chin Chu	1800.0	57	31	5	5	4.2	337.0
3	Butterfly High	1000.0	1815	4	1	5	4.3	1200.0
5	Flea Bazaar Café	800.0	2	41	4	5	4.2	2042.0

	Model Names	Accuracy socre
0	Linear Reg	14.900382
1	Ridge Reg	14.900269
2	Lasso Reg	-0.011738
3	RandomForest Reg	97.477450
4	Support Vector Reg	89.320789

	Actual Ratin	Predicted Rating
0	2.5	3.08
1	3.2	3.28
2	3.4	3.28
3	3.1	3.08
4	3.7	3.66
...	...	...
1146	3.2	3.11
1147	3.0	3.04
1148	3.8	3.68
1149	4.1	4.20
1150	3.6	3.65